Ergebnisse
101 ArtikelSortieren
1:27:30EN
Lex FridmanPodcastFrom NAND Gates to Self-Driving Traffic: Deep Reinforcement Learning in One LectureModeration: Lex FridmanLex Fridman's second MIT 6.S094 lecture walks from the humble perceptron to deep Q-learning and the browser-based DeepTraffic competition.
1:05:15ENLex FridmanPodcastTaming the Long Tail: How Waymo Builds a Self-Driving FactoryModeration: Lex FridmanWaymo principal scientist Drago Anguelov explains how machine learning infrastructure, hybrid design and smart simulated agents tackle the rare events of autonomous driving.
1:27:15ENLex FridmanPodcastPolicy Gradients vs. Q-Learning: John Schulman's Field Guide to Deep Reinforcement LearningModeration: Lex FridmanOpenAI's John Schulman walks through the core methods of deep RL, from the score function estimator to TRPO and DQN, and says when each one is worth using.
1:19:21ENLex FridmanPodcastVapnik's Case for Learning by Predicates, Not Just by More DataModeration: Lex FridmanIn an MIT lecture, Vladimir Vapnik argues that complete statistical learning needs two mechanisms, data and invariants, and that choosing smart predicates is where intelligence lives.
1:03:25ENLex FridmanPodcastTheano in an Hour: Symbolic Graphs, Automatic Gradients and a Compiler That Rewrites Your MathModeration: Lex FridmanPascal Lamblin of MILA walks through how Theano builds, differentiates, optimizes and runs computation graphs, then trains logistic regression, a convnet and an LSTM.
1:08:06ENLex FridmanPodcast · 2 StimmenDeep Learning in One Lecture: From Perceptrons to AutoML and the Limits of LearningGast: Deep Learning Basics · Moderation: Lex FridmanLex Fridman's opening lecture for MIT's 6.S094 course surveys why deep learning took off, how neural networks learn, and where the technique still falls short.
13:58ENLex FridmanPodcastDeep Reinforcement Learning, Explained by the Researcher Behind AlphaGoModeration: Lex FridmanDavid Silver of DeepMind walks through what reinforcement learning is, how its building blocks fit together, and why deep neural networks keep surprising even the experts.
57:55ENLex FridmanPodcastFrom Q-Tables to AlphaGo Zero: A Self-Driving Car Lecture on Deep Reinforcement LearningModeration: Lex FridmanLex Fridman's MIT 6.S094 lecture walks from the AI pipeline and Q-learning to deep Q-networks, AlphaGo Zero and the DeepTraffic competition.
17:35ENLex FridmanPodcastHands Off the Wheel in San Diego: A Comma Two Demo Drive and a Tour of comma.ai's Hardware ShopModeration: Lex FridmanAfter their podcast conversation, George Hotz takes Lex Fridman on an openpilot drive and then through the comma.ai offices, dashboards, assembly line and compute cluster.
1:13:22ENLex FridmanPodcastThe Second 90%: What It Really Takes to Put Deep Learning on a Driverless CarModeration: Lex FridmanWaymo's Sacha Arnoud walks MIT students through Waymo's history, its perception stack, and the industrial-scale labeling, compute and testing behind it.
57:15ENLex FridmanPodcastInside Torch and Autograd: How Deep Learning Libraries Compute GradientsModeration: Lex FridmanAlex Wiltschko of Twitter walks through Lua Torch, then explains automatic differentiation and what separates modern deep learning frameworks.
24:08ENLex FridmanPodcast · 2 StimmenIntelligence Is Not Just Prediction: David Ferrucci on Explanation, Persuasion and Shared MeaningGast: David Ferrucci · Moderation: Lex FridmanThe lead of IBM's Watson team argues that predicting well is only half of intelligence, and that being understood by others is the other half.
1:20:58ENLex FridmanPodcastFrom Bag of Words to Attention: Quoc Le Teaches Sequence-to-Sequence Learning Through Email RepliesModeration: Lex FridmanA Deep Learning School talk that builds sequence-to-sequence models step by step around one running example, automatic email reply, and then surveys memory and operation-augmented networks.
1:19:48ENLex FridmanPodcastBigger Models, Cleaner Splits and Human Baselines: Andrew Ng's Practical Recipe for Applied Deep LearningModeration: Lex FridmanIn a 2016 Deep Learning School talk, Andrew Ng distills lessons from leading Baidu's AI team into a workflow for diagnosing models, handling data and building a career.
1:02:06ENLex FridmanPodcastLearning TensorFlow Hands-On: From a Mystery Line to Handwritten DigitsModeration: Lex FridmanGoogle Brain's Sherry Moore walks a Deep Learning School audience through how TensorFlow works and two core labs, linear regression and MNIST digit recognition.
10:34ENLex FridmanPodcast · 2 StimmenWhy Deep Learning Needs Rules: Chollet on Interpolation, Abstraction and Hybrid AIGast: François Chollet · Moderation: Lex FridmanFrançois Chollet explains why neural networks only interpolate between points they have seen, and why the best AI systems pair them with symbolic rules.
53:13ENLex FridmanPodcastHow Machines Learn to See: From Pixel Differences to Convolutions, ResNets and Scene SegmentationModeration: Lex FridmanLex Fridman's MIT 6.S094 lecture walks from the basics of image classification through landmark network architectures to pixel-level segmentation, optical flow and the SegFuse competition.
34:33ENLex FridmanPodcastTeaching Cars to Watch the Driver: Deep Learning for Semi-Autonomous VehiclesModeration: Lex FridmanLex Fridman's MIT 6.S094 lecture on using driver-facing cameras and neural networks to understand body pose, gaze, emotion and cognitive load.
52:28ENLex FridmanPodcast · 2 StimmenRay Kurzweil on Hierarchies, the Neocortex and Merging with AIGast: Ray Kurzweil · Moderation: Lex FridmanIn an MIT AGI course lecture, Kurzweil connects the history of neural networks to his hierarchical theory of the neocortex, language understanding at Google, longevity, jobs and existential risk.
1:00:15ENLex FridmanPodcast · 2 StimmenCircuit Search, Hindsight and Self-Play: Ilya Sutskever's Case for Where Learning Is GoingGast: Ilya Sutskever · Moderation: Lex FridmanIn an MIT AGI lecture, OpenAI's co-founder explains why deep learning works, then walks through meta-learning, hindsight experience replay, sim-to-real transfer, self-play and learning goals from human feedback.
20:50ENLex FridmanPodcastGlitches as Features: What John Hopfield Says Artificial Neural Networks Are MissingModeration: Lex FridmanIn a short conversation with Lex Fridman, physicist and neural-network pioneer John Hopfield compares evolved brains with today's artificial networks and explains why he expects AI to borrow from biology generation after generation.
11:59ENLex FridmanPodcast · 2 StimmenFrom a Side Project to TensorFlow's Core: François Chollet on How Keras Came to BeGast: François Chollet · Moderation: Lex FridmanThe creator of Keras recalls why he built it in 2015 around recurrent networks, how it moved onto TensorFlow, and what TensorFlow 2.0 means for its design.
26:45ENLex FridmanPodcast · 2 StimmenStart Small, Build Habits, Pick Your Team: Andrew Ng's Practical Advice for Learning Deep LearningGast: Andrew Ng · Moderation: Lex FridmanIn a clip from the Lex Fridman Podcast, Andrew Ng explains how to begin in deep learning, how to study effectively, and how to choose a career path.
1:31:29ENLex FridmanPodcastIs Driving More Like Chess or Conversation? Lex Fridman's Opening Lecture on Deep Learning for Self-Driving CarsModeration: Lex FridmanThe first lecture of MIT 6.S094 introduces neural networks, reinforcement learning and computer vision through the question of how hard driving really is.Mehr laden24 von 101 angezeigt